检索结果-内蒙古大学图书馆

Advances in computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： B. Jansi V. Sumalatha Department of Computer Science Vels Institute of Science Technology and Advanced Studies Chennai Tamil Nadu India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

The effective method for continuously monitoring the fetus’s health is called Cardiotocography (CTG). For the past 60 years, CTG has been used in clinical settings, allowing medical professionals to identify early indicators of fetal deterioration. Prior research has solely focused on the classification accuracy of CTG datasets that include the entire feature set, ignoring the classifier computing time. Improved Gaussian Grasshopper Optimization Algorithm (IGGOA) and Deep Belief Network (DBN) are introduced to categorize CTG data. Several factors contribute to the introduction of IGGOA to feature selection: 1) Due to its fragile tail, Gaussian Mutation (GM) is introduced to generate a new offspring closer to the original feature. 2) The development of Levy Flight (LF) has created a more straightforward way to solve the local optimum because grasshoppers have more vital attraction forces;3) OBL has been used to update the present population, and GOA capability is used to determine the FHR classification. In the DBN classifier, CTG samples are categorized as Normal (N), Suspect (S), and Pathological (P). DBN has been analyzed as a Restricted Boltzmann Machine (RBM). Every sub-network hidden layer in the DBN classifier acts as the layer visible to the layer after it. The Softmax function has been used to determine the hidden layer results. The accuracy is about $97.3659 \%$, which is better than other models.

关键词： Accuracy Fetal heart rate Computational modeling Sociology Tail Feature extraction Probability distribution

来源：评论

学校读者我要写书评

暂无评论

A hybrid technique for selection and minimization of test cases in regression testing

引用

Recent Advances in computer science and Communications 2021年第2期14卷 477-488页

作者： Singh, Leena Singh, Shailendra N. Dawra, Sudhir Department of Computer Science and Engineering Amity University Noida India Department of Computer Application Tecnia Institute of Advanced Studies New Delhi India

Background: In today’s era, modifications in a software is a common requirement by customers. When changes are made to existing software, re-testing of all the test cases is required to ensure that the newly introduced changes do not have any unwanted effect on the behavior of the software. However, re-testing of all the test cases would not only be time consuming but also expensive. Therefore, there is a need for a technique that reduces the number of tests to be performed. Regression testing is one of the ways to reduce the number of test cases. Selection technique is one such method which seeks to identify the test cases that are relevant to some set of recent changes. Objective: It is evident that most of the studies have used different selection techniques and have focused only on one parameter for achieving reduced test suite size without compromising the performance of regression testing. However, to the best of our knowledge, no study has taken two or more parameters of cov-erage, and/or execution time in a single testing. This paper presents a hybrid technique that combines both regression test selection using slicing technique and minimization of test cases using modified firefly algorithm with combination of parameters coverage and execution time in a single testing. Methods: A hybrid technique has been described that combines both selection and minimization. Selection of test cases is based upon slicing technique while minimization is done using firefly algorithm. Hybrid technique selects and minimizes the test suite using information on statement coverage and execution time. Results: The proposed technique gives 43.33% much superior result as compared to the other hybrid approach in terms of significantly reduced number of test cases. It shows that the resultant test cases were effective enough to cover 100% of the statements, for all the programs. The proposed technique was also tested on four different programs namely Quadratic, Triangle, Next day, Co

关键词： Testing

来源：评论

学校读者我要写书评

暂无评论

An Efficient Framework Classification for Diabetic Retinopathy Using MobileNetV2

An Efficient Framework Classification for Diabetic Retinopat...

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Jayaprakash Venugopal Kalaivani Kathirvelu Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Diabetes is a disorder marked by unregulated glucose levels in the body, potentially causing retinal damage and leading to irreversible visual impairment or loss. Diabetes affects the eyes, resulting in diabetic retinopathy, a prevalent medical disorder, especially among the elderly. Consequently, timely and precise diabetic retinopathy screening is essential for disease prediction. Nonetheless, conventional manual detection is labor-intensive and often results in misdiagnosis for several individuals. In this study, we devised a deep learning (DL) model using transfer learning from the MobileNetV2 architecture, accompanied with an innovative color version preprocessing approach. It decreased the training duration and achieved an average accuracy of 0.93 when applied to the new Kaggle dataset “APTOS 2019 Blindness Detection.” Furthermore, to mitigate the issue of overfitting in the long term, we used Stratified K-fold cross-validation.

关键词： Training Deep learning Diabetic retinopathy Accuracy Visual impairment Transfer learning computer architecture Color Blindness Overfitting

来源：评论

学校读者我要写书评

暂无评论

Diverse Image Processing Techniques for Machine Learning Methods

Diverse Image Processing Techniques for Machine Learning Met...

引用

IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS)

作者： A. Bhagya S. Perumal Department of Computer Science Vels Institute of science Technology and Advanced Studies Chennai Tamil Nadu India

ISBN: (数字)9798350361186

ISBN: (纸本)9798350361193

Machine learning is a trending topic in the area of computer vision, which makes the machine able to learn about it without being expressly programmed using various algorithms. When a model is designed to predict future-based on historical data using machine learning algorithms, data is vital because high quality data is needed to run the model efficiently and to predict highly accurate results. Machine learning algorithms receive data in many forms, like audio (speech recognition), images (feature recognition), numeric data (like height and weight) etc. When it comes to computer vision, the machine learning algorithms must be able to understand the image data, and before the images are processed to the algorithms it should be pre-processed (cleaned and set to the desired format) using various image pre-processing techniques. This research paper presents various image processing techniques, literature reviews on various image processing techniques and image PSNR value after applying median filter, grayscale filter and box filters.

关键词： Machine learning algorithms Image processing Signal processing algorithms Speech recognition Machine learning Gray-scale Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

A Mango Disease Prediction for Smart Agiculture using Machine Learning Algorithms

A Mango Disease Prediction for Smart Agiculture using Machin...

引用

International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： Lavanya K A. Packialatha Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies Chennai Tamilnadu India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

The country's economy relies heavily on agriculture, and the health of the crops is essential to its success. Crop diseases that go undetected can cost the agriculture industry. Thus early detection and identification are crucial. It is possible to avoid crop diseases from destroying the harvest if they are accurately diagnosed and detected. Because healthy and diseased plants appear identical in their early stages, farmers cannot distinguish between the two by watching the crop leaf. India exports vast mangoes, making it an economically and environmentally significant fruit. About 1500 mango species are grown in India, with over 1000 commercial types. There are a lot of diseases that harm mangoes, affecting their look, taste, and economy. The "Prediction of Disease in Mango Fruit Crops" A complex warning system that uses machine learning and IoT. One of the main objectives is to develop a system that can forecast disease outbreaks on mango fruit harvests using historical weather information and crop yield Mango trees in India are plagued by a fungus called Anthracnose, which is the most frequent disease of its kind. Anthracnose, a highly contagious fungus, requires a quick and accurate method of diagnosis. As a result, an in-depth examination of the plants is essential before initiating any control measures. This study examines machine learning(ML) and deep learning (DL) strategies for detecting and classifying mango plant diseases. The performance of ML and DL-based classification models for mango crops and their datasets and feature extraction approachesare examined in this work. Finally, a variety of issues involved in plant disease identification are explored.

关键词： Support vector machines Deep learning Plant diseases Accuracy Costs Biological system modeling Crops Data models Agriculture Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Harvesting Insights: Predicting Vegetable Prices with Hybrid CLA-Conv BiGRU Techniques 3

Harvesting Insights: Predicting Vegetable Prices with Hybrid...

引用

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Lal Ambashtha, Kanahaiya Praveen Kumar, Chatakunta Pandey, Vivekanand Sakthivel Padaiyatchi, S. Bharathi, A. Navaz, K. Gnsu Faculty of Information Technology Bihar Sasaram India Institute of Aeronautical Engineering Department of Computer Science and Engineering Hyderabad India Amity University Bihar Patna India Nehru Institute of Engineering and Technology Department of Electrical and Electronics Engineering TN Coimbatore India Vels Institute of Science Technology and Advanced Studies Department of Information Technology Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350381931

The system delves into the important topic of agricultural market pricing, with a specific emphasis on the ever-changing realm of vegetable supply and prices. Stabilizing the supply and prices of vegetables becomes an enormous task when consider that the system are grown outdoors and that weather variables significantly impact harvests. Such unpredictability has far-reaching consequences for the country's economy, highlighting the critical need to develop efficient methods of precise forecasting. The government has made multiple attempts to stabilize vegetable prices and supplies, but these have all been unsuccessful due to the unpredictable weather patterns of late. This system uses state-of-the-art deep learning methods, notably the Hybrid CLA-Conv BiGRU model, which incorporates a novel preprocessing strategy based on the HP Filter, to conquer this obstacle. A strong prediction model for vegetable prices is constructed using the process, which includes feature extraction, scoring, and selection. © 2024 IEEE.

关键词： Vegetables

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Identification From Retinal Images With The Use Of A Deep Learning-Based Transfer Training Framework

Diabetic Retinopathy Identification From Retinal Images With...

引用

Integration of Emerging Technologies for the Digital World (ICIETDW), International Conference on

作者： Jayaprakash Venugopal Kalaivani Kathirvelu Department of Computer Science and Engineering Vels Institute of Science Technology & Advanced Studies (VISTAS) Chennai India

ISBN: (数字)9798331541170

ISBN: (纸本)9798331541187

Diabetic retinopathy (DR) is a major contributor to vision loss worldwide, highlighting the urgent need for early identification and prompt care to prevent further deterioration of vision. Diagnosing DR is intrinsically difficult, since it requires the thorough evaluation of complex retinal images by skilled professionals. DR, a consequence of diabetes, has the potential to cause vision loss if not identified in its early stages. research presents a novel model that utilizes transfer learning to detect diabetic retinopathy. The first trials yielded poor accuracies for both training and validation. The categorization of class-4, especially those depicting severe instances, yielded unexpected outcomes, since several images were categorized as moderate. Consequently, more investigation is required to ascertain the accuracy of these classifications. Therefore, our suggested approach allows for easy classification of the retina pictures of both Diabetic and Healthy individuals, resulting in a decrease in the number of evaluations required by medical specialists.

关键词： Training Diabetic retinopathy Accuracy Transfer learning Refining Retina Data augmentation Robustness Research and development Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Efficient Dengue Spread Prediction Using Machine Learning Models with Various Preprocessing Techniques

Efficient Dengue Spread Prediction Using Machine Learning Mo...

引用

Advances in computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： K. Saraswathi K. Rohini Department of Computer Science Vels Institute of Science Technology and Advanced Studies Chennai Tamil Nadu India

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

The viral disease dengue, spread by mosquitoes, is a severe hazard to public health worldwide. Predicting dengue outbreaks is an essential field of study that aims to stop and lessen the effects of the virus spread by mosquitoes. Utilizing modern technologies like data analytics and ML(Machine Learning) will significantly improve the capacity to predict and contain dengue outbreaks. The work examines how the effectiveness of Convolutional Neural Networks (CNNs) in forecasting and evaluating Dengue outbreaks is affected by several scaling strategies, including Min-Max Scaling, Z-Score Standardization, and Robust Scaling. For disease control to be effective, outbreaks must be predicted with accuracy and timeliness. Before feeding the input data into the CNN architecture, preprocess takes place in experiments utilizing Robust Scaling, Z-Score Standardization, and Min-Max Scaling. The model is methodically assessed using necessary measures like recall, accuracy, and precision. The findings show that robust scaling consistently performs better than the other scaling methods, improving CNN’s capacity to identify characteristics and patterns important for predicting Dengue outbreaks. The result was that Robust Scaling+CNN gave the best results, with an accuracy of $93 \%$, precision, and recall of 0.92 and 0.85, respectively. The tool used for execution is Python.

关键词： Accuracy Recurrent neural networks Standardization Predictive models Data models Numerical models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep learning: Spatial-Temporal road traffic data congestion using Agglomerative Clustering

Deep learning: Spatial-Temporal road traffic data congestion...

引用

International Conference on Electrical Energy Systems (ICEES)

作者： S. Senthilarasi S. Kamalakkannan Department of Computer Science School of Computing Sciences Vels Institute of Science Technology ampersand Advanced Studies (VISTAS) Pallavaram Chennai India

In the long run of road traffic data especially in urbanization due to people migration because of employment and other factors still it is a challenging issue in daily life to recover the congestion. In our paper, the causes of road traffic data and its measures have been shown. The algorithm to alternate the route for people in case of traffic has been displayed in flowchart. The different types of traffic sign detection to alert the people in common on road traffic has been discussed with colors. The estimation of road traffic congestion is computed using necessary formulas has been shown. Various measures have been calculated show the higher accuracy of agglomerative clustering compared with other models. The experimental study has been shown in Real Time traffic data of Chenmai city from the year 2015 to 2021. In addition, drastic measures to control road traffic congestion has been discussed for present and future.

关键词： Flowcharts Image color analysis Roads Urban areas Clustering algorithms Estimation Energy measurement

来源：评论

学校读者我要写书评

暂无评论

Exploring Convolution Neural Networks for Image Classification in Medical Imaging 2

Exploring Convolution Neural Networks for Image Classificati...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in computing, Electrical and Electronics, ICIITCEE 2024

作者： Vishwa Priya, V. Chattu, Padmini Sivasankari, K. Pisal, Dnyaneshwar Tukaram Renuka Sai, Bantupalli Suganthi, D. Vels Institute Science Technology and Advanced Studies Department of Cs Tamilnadu Chennai India Ace Engineering College India Sri Sai Ram Institute of Technology Department of Ece Tamilnadu Chennai India SVPMs Institute of Management Baramati Pune Maharashtra Malegaon India Raghu Engineering College Computer Science and Engineering Visakhapatnam India Saveetha College of Liberal Arts and Sciences Simats Department of Computer Science Thandalam Chennai India

ISBN: (纸本)9798350306415

Modern healthcare relies on medical imaging to diagnose and cure diseases. Convolution Neural Networks (CNNs) have excelled at image categorization, and their use in medical imaging could change illness diagnosis. This study examines CNN's medical picture categorization performance. This study used X-rays, CT scans, MRIs, and histopathology slides. Traditional CNNs, transfer learning models, and bespoke networks were constructed and trained. The training data included lung ailments, cancer detection, bone fractures, and neurological disorders. Our investigations showed that CNNs can extract complex characteristics from medical photos, improving classification accuracy. Transfer learning, where pre-trained models were fine-tuned on medical data, performed well with 94.8% accuracy. We used cutting-edge data augmentation and attention strategies to improve model generalization and interpretability. In addition to high classification accuracy, we studied model explainability using gradient-based methods and visualization to highlight medical picture regions of relevance that influenced model predictions. Building trust with medical practitioners and understanding deep learning model decision-making requires interpretability. In clinical settings, CNN deployment raises ethical and practical issues such as data privacy, model robustness, and regulatory compliance. According to our research, CNNs may increase medical picture classification accuracy and speed. X-rays had the best accuracy at 95.2%, followed by CT scans at 92.7% and MRIs at 94.1%. Histopathological slides exhibited 88.6% accuracy;however, this shows that CNNs can diagnose diseases from microscopic images. © 2024 IEEE.

关键词： Convolutional Neural Networks Image Classification Medical Data Analysis Medical Imaging

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：